OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models
Published in ArXiv Preprint, 2025
We present OpenEthics, a comprehensive ethical evaluation framework for open-source generative large language models. Our work assesses LLM ethical performance across Turkish and English, developing reliability datasets and implementing LLM judge and rejection evaluation pipelines for automated assessment.
Recommended citation: Yıldırım Özen, Erinç Çetin, Kaan Engür, Elif Naz Demiryılmaz, Çağrı Toraman. (2025). "OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models." ArXiv Preprint.
Download Paper